Feature-based Machine Learning Research Articles

Machine Learning-Based Feature Extraction and Selection

Machine Learning-Based Feature Extraction and Selection

O-025 An artificial intelligence (AI) model non-invasively evaluates endometrial receptivity from ultrasound images, surpassing endometrial thickness (EMT) in predicting implantation

Abstract Study question Can an AI image-based model be trained to predict whether an endometrium, prior to progesterone, is receptive for successful embryo implantation from ultrasound images? Summary answer An endometrial receptivity AI model, utilizing ultrasound images and clinical features, is predictive of successful implantation and outperforms endometrial thickness as a predictor of implantation. What is known already Despite its importance in successful embryo implantation and subsequent live birth, endometrial receptivity is difficult to measure. The standard of care at some clinics is to cancel an embryo transfer if EMT is measuring less than 7 mm on ultrasound assessment – however, achieving an EMT threshold does not guarantee success, even with euploid blastocysts. Currently available receptivity tests (e.g. endometrial receptivity assays) are unreliable and have not shown significant improvements in reproductive outcomes, necessitating the development of new evaluation methods for endometrial receptivity. AI can potentially address this gap in clinical care and understanding, aiming to increase patient success. Study design, size, duration 79,602 ultrasound images (40,910 patients) of the endometrium, on the day of progesterone start according to patient’s frozen embryo transfer cycle, were retrospectively collected from 4 clinic networks including 70 clinic locations. PGT-A outcomes and blastocyst quality were available for 15,466 and 36,070 blastocysts respectively, with 14,538 having labels for both. Different image samples (based on embryo quality) were selected to train and test several AI models, with implantation (positive beta-hCG) as a binary outcome. Participants/materials, setting, methods Three criteria for negative (implantation) class sample selection were tested for receptivity model development: 1) high- or medium-quality and/or euploid blastocysts; 2) high-quality blastocysts; 3) all blastocysts. Models were ensembles consisting of an image-based deep learning (DL)-model and a feature-based machine learning (ML)-model. Model performance was measured by Area-under-the-curve (AUC), sensitivity, and specificity. Feature importance from the ML model was assessed, while receptivity model performance was compared to the power of EMT to predict implantation. Main results and the role of chance A receptivity model trained on scenario 1) (n = 27,424) achieved AUC 0.613, sensitivity 0.716, and specificity 0.439 on a test set of 9197 samples, in predicting implantation. Another receptivity model trained on scenario 2) (n = 25,625) achieved AUC 0.627, sensitivity 0.637, and specificity 0.543 on a test set of 8642. Whereas a third receptivity model trained on scenario 3) (n = 31,238) was selected for further analysis as it attained the best performance with AUC 0.631, sensitivity 0.628, and specificity 0.556 on a test set of 10,422. The ensemble model also utilizes relevant clinical features, which were ranked by importance to model predictions: EMT; progesterone blood test value; age at transfer; previous total embryo transfers; days between ultrasound date and transfer date; age at retrieval; and oocyte origin. EMT was assessed for its ability to predict implantation at thresholds between 5–20 mm. The threshold that best separates positive and negative implantation was determined by evaluating AUC on a validation set of 5682. A threshold of 8.8 mm achieved an AUC 0.576, sensitivity 0.694, and specificity 0.455 in predicting implantation on a test set of 5686. However, the receptivity model AUC (0.631) was significantly higher (p < 0.001; DeLong test for differences in AUC), outperforming EMT predictability. Limitations, reasons for caution The endometrial receptivity model was built and tested on retrospective frozen embryo transfer data. Results should be corroborated in prospective and non-selection studies, as well as in multiple geographical locations (all clinics included reside in the United States). The dataset requires greater diversification, with a greater representation of EMT (<7mm). Wider implications of the findings This study indicates that an AI model can be built to predict implantation from ultrasound images and clinical features, surpassing current standards - EMT alone. Further experimentation, with additional clinical features, may improve performance to facilitate development of a model that can accurately predict the gold-standard of live birth. Trial registration number Not applicable

Machine Learning-Based Feature Extraction and Classification of EMG Signals for Intuitive Prosthetic Control

Signals play a fundamental role in science, technology, and communication by conveying information through varying patterns, amplitudes, and frequencies. This paper introduces innovative methodologies for processing electromyographic (EMG) signals to develop artificial intelligence systems capable of decoding muscle activity for controlling arm movements. The study investigates advanced signal processing techniques and machine learning classification algorithms using the GRABMyo dataset, aiming to enhance prosthetic control systems and rehabilitation technologies. A comprehensive analysis was conducted on signal processing techniques, including signal filtering and discrete wavelet transform (DWT), alongside a composite feature set comprising Mean Absolute Value (MAV), Waveform Length (WL), Zero Crossing (ZC), Slope Sign Changes (SSC), Root Mean Square (RMS), Enhanced Waveform Length (EWL), and Enhanced Mean Absolute Value (EMAV). These features, refined through Linear Discriminant Analysis (LDA) for dimensionality reduction, were classified using Support Vector Machine (SVM) algorithms. Signal filtering and DWT improved signal quality, facilitating better feature extraction, while the diverse feature set enhanced classification accuracy. LDA further improved accuracy by isolating the most informative features, and the SVM achieved optimal performance in decoding complex EMG patterns. Machine learning models, including K-Nearest Neighbor (KNN), Naïve Bayes (NB), and the SVM, were evaluated, with the SVM outperforming the others. The significance of these results lies in their potential applications in prosthetic control systems and rehabilitation technologies. By accurately decoding muscle activity, the developed systems can facilitate more intuitive and responsive robotic arm movements, contributing to the advancement of innovative solutions for individuals requiring prosthetic devices or undergoing rehabilitation, hence improving the quality of life for users. This research marks a significant step forward in the integration of advanced signal processing and machine learning in the field of EMG analysis.

Metagenomic insights into microbial adaptation to the salinity gradient of a typical short residence-time estuary

BackgroundMicrobial adaptation to salinity has been a classic inquiry in the field of microbiology. It has been demonstrated that microorganisms can endure salinity stress via either the “salt-in” strategy, involving inorganic ion uptake, or the “salt-out” strategy, relying on compatible solutes. While these insights are mostly based on laboratory-cultured isolates, exploring the adaptive mechanisms of microorganisms within natural salinity gradient is crucial for gaining a deeper understanding of microbial adaptation in the estuarine ecosystem.ResultsHere, we conducted metagenomic analyses on filtered surface water samples collected from a typical subtropical short residence-time estuary and categorized them by salinity into low-, intermediate-, and high-salinity metagenomes. Our findings highlighted salinity-driven variations in microbial community composition and function, as revealed through taxonomic and Clusters of Orthologous Group (COG) functional annotations. Through metagenomic binning, 127 bacterial and archaeal metagenome-assembled genomes (MAGs) were reconstructed. These MAGs were categorized as stenohaline—specific to low-, intermediate-, or high-salinity—based on the average relative abundance in one salinity category significantly exceeding those in the other two categories by an order of magnitude. Those that did not meet this criterion were classified as euryhaline, indicating a broader range of salinity tolerance. Applying the Boruta algorithm, a machine learning-based feature selection method, we discerned important genomic features from the stenohaline bacterial MAGs. Of the total 12,162 COGs obtained, 40 were identified as important features, with the “inorganic ion transport and metabolism” COG category emerging as the most prominent. Furthermore, eight COGs were implicated in microbial osmoregulation, of which four were related to the “salt-in” strategy, three to the “salt-out” strategy, and one to the regulation of water channel activity. COG0168, annotated as the Trk-type K+ transporter related to the “salt-in” strategy, was ranked as the most important feature. The relative abundance of COG0168 was observed to increase with rising salinity across metagenomes, the stenohaline strains, and the dominant Actinobacteriota and Proteobacteria phyla.ConclusionsWe demonstrated that salinity exerts influences on both the taxonomic and functional profiles of the microbial communities inhabiting the estuarine ecosystem. Our findings shed light on diverse salinity adaptation strategies employed by the estuarine microbial communities, highlighting the crucial role of the “salt-in” strategy mediated by Trk-type K+ transporters for microorganisms thriving under osmotic stress in the short residence-time estuary.22YT9hkSS5Zn-gk-qyndrEVideo

An algorithm to detect dicrotic notch in arterial blood pressure and photoplethysmography waveforms using the iterative envelope mean method

Background and objectiveDetection of the dicrotic notch (DN) within a cardiac cycle is essential for assessment of cardiac output, calculation of pulse wave velocity, estimation of left ventricular ejection time, and supporting feature-based machine learning models for noninvasive blood pressure estimation, and hypotension, or hypertension prediction. In this study, we present a new algorithm based on the iterative envelope mean (IEM) method to detect automatically the DN in arterial blood pressure (ABP) and photoplethysmography (PPG) waveforms. MethodsThe algorithm was evaluated on both ABP and PPG waveforms from a large perioperative dataset (MLORD dataset) comprising 17,327 patients. The analysis involved a total of 1,171,288 cardiac cycles for ABP waveforms and 3,424,975 cardiac cycles for PPG waveforms. To evaluate the algorithm's performance, the systolic phase duration (SPD) was employed, which represents the duration from the onset of the systolic phase to the DN in the cardiac cycle. Correlation plots and regression analysis were used to compare the algorithm against marked DN detection, while box plots and Bland-Altman plots were used to compare its performance with both marked DN detection and an established DN detection technique (second derivative). The marking of the DN temporal location was carried out by an experienced researcher using the help of the 'find_peaks' function from the scipy Python package, serving as a reference for the evaluation. The marking was visually validated by both an engineer and an anesthesiologist. The robustness of the algorithm was evaluated as the DN was made less visually distinct across signal-to-noise ratios (SNRs) ranging from -30 dB to -5 dB in both ABP and PPG waveforms. ResultsThe correlation between SPD estimated by the algorithm and that marked by the researcher is strong for both ABP (R2(87,343) =0.99, p<.001) and PPG (R2(86,764) =0.98, p<.001) waveforms. The algorithm had a lower mean error of DN detection (s): 0.0047 (0.0029) for ABP waveforms and 0.0046 (0.0029) for PPG waveforms, compared to 0.0693 (0.0770) for ABP and 0.0968 (0.0909) for PPG waveforms for the established 2nd derivative method. The algorithm has high rate of detectability of DN detection for SNR of >= -9 dB for ABP waveforms and >= -12 dB for PPG waveforms indicating robust performance in detecting the DN when it is less visibly distinct. ConclusionOur proposed IEM- based algorithm can detect DN in both ABP and PPG waveforms with low computational cost, even in cases where it is not distinctly defined within a cardiac cycle of the waveform (‘DN-less signals’). The algorithm can potentially serve as a valuable, fast, and reliable tool for extracting features from ABP and PPG waveforms. It can be especially beneficial in medical applications where DN-based features, such as SPD, diastolic phase duration, and DN amplitude, play a significant role.

Interpretable machine learning model for predicting acute kidney injury in critically ill patients

BackgroundThis study aimed to create a method for promptly predicting acute kidney injury (AKI) in intensive care patients by applying interpretable, explainable artificial intelligence techniques.MethodsPopulation data regarding intensive care patients were derived from the Medical Information Mart for Intensive Care IV database from 2008 to 2019. Machine learning (ML) techniques with six methods were created to construct the predicted models for AKI. The performance of each ML model was evaluated by comparing the areas under the curve (AUC). Local Interpretable Model-Agnostic Explanations (LIME) method and Shapley Additive exPlanation values were used to decipher the best model.ResultsAccording to inclusion and exclusion criteria, 53,150 severely sick individuals were included in the present study, of which 42,520 (80%) were assigned to the training group, and 10,630 (20%) were allocated to the validation group. Compared to the other five ML models, the eXtreme Gradient Boosting (XGBoost) model greatly predicted AKI following ICU admission, with an AUC of 0.816. The top four contributing variables of the XGBoost model were SOFA score, weight, mechanical ventilation, and the Simplified Acute Physiology Score II. An AKI and Non-AKI cases were predicted separately using the LIME algorithm.ConclusionOverall, the constructed clinical feature-based ML models are excellent in predicting AKI in intensive care patients. It would be constructive for physicians to provide early support and timely intervention measures to intensive care patients at risk of AKI.

Machine learning with electrocardiograms to optimize mortality risk stratification in patients with suspected acute coronary syndrome

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Heart, Lung, and Blood Institute (NHLBI) and National Center for Advancing Translational Sciences (NCATS). Background The importance of risk stratification in patients with suspected acute coronary syndrome (ACS) extends beyond diagnosis and immediate treatment. It influences the precision of care delivery and the allocation of resources to those at highest risk of adverse events. Purpose We sought to evaluate the prognostic value of electrocardiogram (ECG) feature-based machine learning models to risk-stratify long-term mortality in those with suspected ACS. Methods This was a multicenter prospective observational cohort study of consecutive, non-traumatic patients evaluated at the emergency department for suspected ACS. The derivation cohort included 4,015 patients from a University Medical Center (age 59±16 years, 47% women, 80% training with 10-fold cross-validation and 20% testing). Ascertainment of all-cause death was based on numerous data sources, including the Centers for Disease Control and Prevention’s National Death Index registry. We trained six machine learning methods for survival analysis using 73 morphological ECG features from presenting prehospital 10-second 12-lead ECGs. We used predicted risk scores in a variational Bayesian Gaussian mixture model to define three risk groups corresponding to low, moderate, and high-risk and compared the resulting classification performance against the HEART score. The external testing cohort included 3,095 patients from a University (age 59±15 years, 44% women). Results The mortality rate was 20.3% in the derivation cohort after an average follow-up period of 3.53 years (IQR 1.75 - 5.32). Extra Survival Trees outperformed other forecasting models during cross-validation. In the internal testing cohort, the derived risk groups were significantly predictive of survival (Kaplan-Meier log-rank test statistic = 121.14, p&amp;lt;0.001), outperforming the classification performance using the HEART score (Figure 1). Our machine learning-based risk stratification model detected &amp;gt;90% of death events missed by low-risk HEART score (Figure 2). Ruling-out the low-risk group, it achieved a negative predictive value of 93.4% with a sensitivity of 85.9% (compared to 89.0% and 75.0%, respectively, for the HEART score). This classification performance generalized well to our external testing cohort. Compared to those in the low-risk group, patients at moderate (OR = 3.62 [1.35-9.74]) and high (OR = 6.12 [2.38-15.75]) risk had significantly higher odds of 30-day cardiovascular death (n=109, 3.5%). Conclusions Using only features from the 10-second 12-lead ECG, we derived and externally validated a machine learning model that stratifies the mortality risk of patients during long-term follow up. This model outperformed current standard of care based on the HEART score. Future work should validate the potential of this decision-support tool in influencing treatment plans and resource allocation.Figure 1.Clustering performanceFigure 2.Sankey diagram

Bacterial Disease Detection of Cherry Plant Using Deep Features

Although the cherry plant is widely grown in the world and Turkey, it is a fruit tree that is difficult to grow and maintain. It can be exposed to various pesticide diseases, especially during fruiting. Today, approaches based on expert reviews and analyses are used for the identification of these diseases. In addition, cherry producers are trying to detect diseases with their knowledge based on experience. Computer-aided agricultural analysis systems are also being developed depending on the rapid developments in technology. These systems help to monitor all processes from planting, cultivation, and harvesting of agricultural products and to make decisions to grow the products healthily. One of the most important issues to be detected and monitored with these systems is plant diseases. The features of the cherry plant disease will be determined by using a pre-trained convolutional neural network (CNN) model which is DarkNet-19, within the scope of this study. These machine learning-based features have been used for the detection of bacteria-based diseases commonly seen on the leaves of cherry plants. The acquired features are classified with Linear Discriminant Analysis, K-Nearest Neighbor, and Support Vector Machine classifiers to solve the multi-class problem including diseased (less and very) and healthy plants. The experimental results show that a success rate of 88.1% was obtained in the detection of the disease.

BrainBeats as an Open-Source EEGLAB Plugin to Jointly Analyze EEG and Cardiovascular Signals.

The interplay between the brain and the cardiovascular systems is garnering increased attention for its potential to advance our understanding of human physiology and improve health outcomes. However, the multimodal analysis of these signals is challenging due to the lack of guidelines, standardized signal processing and statistical tools, graphical user interfaces (GUIs), and automation for processing large datasets or increasing reproducibility. A further void exists in standardized EEG and heart-rate variability (HRV) feature extraction methods, undermining clinical diagnostics or the robustness of machine learning (ML) models. In response to these limitations, we introduce the BrainBeats toolbox. Implemented as an open-source EEGLAB plugin, BrainBeats integrates three main protocols: 1) Heartbeat-evoked potentials (HEP) and oscillations (HEO) for assessing time-locked brain-heart interplay at the millisecond accuracy; 2) EEG and HRV feature extraction for examining associations/differences between various brain and heart metrics or for building robust feature-based ML models; 3) Automated extraction of heart artifacts from EEG signals to remove any potential cardiovascular contamination while conducting EEG analysis. We provide a step-by-step tutorial for applying these three methods to an open-source dataset containing simultaneous 64-channel EEG, ECG, and PPG signals. Users can easily fine-tune parameters to tailor their unique research needs using the graphical user interface (GUI) or the command line. BrainBeats should make brain-heart interplay research more accessible and reproducible.

Comparative analysis of feature-based ML and CNN for binucleated erythroblast quantification in myelodysplastic syndrome patients using imaging flow cytometry data

Myelodysplastic syndrome is primarily characterized by dysplasia in the bone marrow (BM), presenting a challenge in consistent morphology interpretation. Accurate diagnosis through traditional slide-based analysis is difficult, necessitating a standardized objective technique. Over the past two decades, imaging flow cytometry (IFC) has proven effective in combining image-based morphometric analyses with high-parameter phenotyping. We have previously demonstrated the effectiveness of combining IFC with a feature-based machine learning algorithm to accurately identify and quantify rare binucleated erythroblasts (BNEs) in dyserythropoietic BM cells. However, a feature-based workflow poses challenges requiring software-specific expertise. Here we employ a Convolutional Neural Network (CNN) algorithm for BNE identification and differentiation from doublets and cells with irregular nuclear morphology in IFC data. We demonstrate that this simplified AI workflow, coupled with a powerful CNN algorithm, achieves comparable BNE quantification accuracy to manual and feature-based analysis with substantial time savings, eliminating workflow complexity. This streamlined approach holds significant clinical value, enhancing IFC accessibility for routine diagnostic purposes.

A Features Based Machine Learning Prediction Model for Sentiment Analysis on Social Media

Sentiment analysis is discovering the current ideology opinion of a group of people and their thoughts. The Sentiment analysis based onthe natural reaction of people on social media platform to reflect their mantel status and state. The main poupose of sentiment analysis is to dealing with society's environment and its impact effects towards the media world and surrounding environment. However, this is the key task of understanding every part of the world. The evolution of feeling simulates the sentiment behaviours to shows different direction of reactions and feeling across time. It can help users obtain a more advanced and detailed understanding of the views and attitudes represented in the content provided by users. The development of social media platforms, such as journals, forums, blogs, micro-blogs, Twitter, and social networks, has fostered sentiment analysis. Competitive advantages for organizations are collecting corporate social media and implementing machine learning algorithms to get valuable insights. In this study, our tasks are to show Bag of Words (BoW) and Term-Frequency-Inverse-Document-Frequency (tf_idf) feature-based machine learning prediction models that can help with sentiment analysis and figure out what their customers need and want from company items. Market research is perhaps the most important field for sentiment analysis applications, aside from brand perception and customer opinion surveys and feedbacks. This study results analysis shows the crucial way of classifying social media tweets feedback into positive or negative categories via using the classifier as a baseline to demonstrate in what manner comments are important based on features for any business model and their result.

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models.

Landslide susceptibility mapping is essential for reducing the risk of landslides and ensuring the safety of people and infrastructure in landslide-prone areas. However, little research has been done on the development of well-optimized Elman neural networks (ENN), deep neural networks (DNN), and artificial neural networks (ANN) for robust landslide susceptibility mapping (LSM). Additionally, there is a research gap regarding the use of Bayesian optimization and the derivation of SHapley Additive exPlanations (SHAP) values from optimized models. Therefore, this study aims to optimize DNN, ENN, and ANN models using Bayesian optimization for landslide susceptibility mapping and derive SHAP values from these optimized models. The LSM models have been validated using the receiver operating characteristics curve, confusion matrix, and other twelve error matrices. The study used six machine learning-based feature selection techniques to identify the most important variables for predicting landslide susceptibility. The decision tree, random forest, and bagging feature selection models showed that slope, elevation, DFR, annual rainfall, LD, DD, RD, and LULC are influential variables, while geology and soil texture have less influence. The DNN model outperformed the other two models, covering 7839.54 km2 under the very low landslide susceptibility zone and 3613.44 km2 under the very high landslide susceptibility zone. The DNN model is better suited for generating landslide susceptibility maps, as it can classify areas with higher accuracy. The model identified several key factors that contribute to the initiation of landslides, including high elevation, built-up and agricultural land use, less vegetation, aspect (north and northwest), soil depth less than 140 cm, high rainfall, high lineament density, and a low distance from roads. The study's findings can help stakeholders make informed decisions to reduce the risk of landslides and ensure the safety of people and infrastructure in landslide-prone areas.

Abstract LB393: Exosome based multiomics combined with cfDNA methylation reveals complementary signatures in blood based liquid biopsy that carry promise for minimally invasive colorectal cancer screening

Abstract Introduction: Colorectal cancer (CRC) ranks second in cancer morbidity, with approximately 60% of patients being diagnosed at an advanced stage. Here, we apply a multiomic strategy jointly leveraging plasma cell-free DNA (cfDNA) and multiple extracellular vesicle (EV)-derived analytes to enhance CRC diagnostic accuracy. Materials and Methods: Plasma was collected from 96 individuals, 48 CRC patients (stage II-IV) and 48 CRC-negative healthy controls. EVs and cfDNA were isolated from the same plasma sample to look at complementary information within the sample. We developed an EV RNA sequencing platform targeting mRNAs and long non-coding RNAs and sequenced to a depth of 50M reads per sample; cfDNA methylome profiling was sequenced to an equivalent depth. The Olink platform profiled proteins both directly from plasma and from isolated EVs. Expression of EV-derived RNA, splice variants, and proteins in addition to cfDNA methylation patterns were analyzed using Bio-Techne’s multiomic platform. Machine learning-based feature selection algorithms identified biomarker signatures from each analyte. Receiver-operator characteristic curves (ROC) were generated utilizing leave-one-out cross-validation of naïve Bayes classifier models to compute the area under the curve (AUC). Individual signatures were integrated to generate a multiomic classifier. Results: Differential gene expression (DEx) analysis identified ~1000 DEx genes with significant enrichment of CRC-relevant pathways. Splice variant analysis identified several genes previously implicated in CRC with differential isoform usage. Over 1.7 million differentially methylated bases were detected between CRC-positive and CRC-negative cohorts. Segmentation of the genome using out-of-bag reference data yielded ~1100 genomic segments, many of which overlap previously reported CRC biomarkers and identified unique information about the CRC status. Proteomic analysis identified several differentially abundant markers with high discriminatory power. Following feature selection analysis, AUCs obtained from top 10 features of RNA expression, splice variants, cfDNA methylation, and protein abundance with an integrative analysis identified a multi-analyte signature, with an overall AUC of 0.99. Conclusion: While biomarker signatures obtained from each analyte in this study resulted in effective separation of CRC status, the multiomic signature further improved the discriminatory power—underscoring the complementary nature of the signals. Thus, a multiomic biomarker discovery strategy leveraging cfDNA and EV cargo holds tremendous promise for minimally invasive screening and potential detection of early-stage cancers, which is currently under further investigation. Citation Format: Kyle Manning, Dulaney Miller, Yang Yang, Jeff Cole, Shuran Xing, Christopher Benway, Christian Ray, Sudipto Chakrabortty, Brian Haynes, Seth Yu, Johan Skog. Exosome based multiomics combined with cfDNA methylation reveals complementary signatures in blood based liquid biopsy that carry promise for minimally invasive colorectal cancer screening [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB393.

Driving behavior-guided battery health monitoring for electric vehicles using extreme learning machine

An accurate estimation of the state of health (SOH) of batteries is critical to ensuring the safe and reliable operation of electric vehicles (EVs). Feature-based machine learning methods have exhibited enormous potential for rapidly and precisely monitoring battery health status. However, simultaneously using various health indicators (HIs) may weaken estimation performance due to feature redundancy. Furthermore, ignoring real-world driving behaviors can lead to inaccurate estimation results as some features are rarely accessible in practical scenarios. To address these issues, we proposed a feature-based machine learning pipeline for reliable battery health monitoring, enabled by evaluating the acquisition probability of features under real-world driving conditions. We first summarized and analyzed various individual HIs with mechanism-related interpretations, which provide insightful guidance on how these features relate to battery degradation modes. Moreover, all features were carefully evaluated and screened based on estimation accuracy and correlation analysis on three public experimental battery degradation datasets. Finally, the scenario-based feature fusion and acquisition probability-based practicality evaluation method construct a useful tool for feature extraction with consideration of driving behaviors. This work highlights the importance of balancing the performance and practicality of HIs during the development of feature-based battery health monitoring algorithms.

Heuristically Optimized Features Based Machine Learning Technique for Identification and Classification of Faults in PV Array

Heuristically Optimized Features Based Machine Learning Technique for Identification and Classification of Faults in PV Array

Identification of Autoantigen Markers for SARS CoV-2 Infection with Machine Learning-based Feature Selection: An Insight into COVID Symptoms

Background and Introduction:: Severe acute respiratory syndrome coronavirus 2 (SARS CoV-2) infection has been shown to trigger autoimmunity, and the phenomenon leads to several chronic human diseases such as Type-1 diabetes, Crohn’s disease, vasculitis, Guillian-Barrė syndrome, etc. The mechanism underlying SARS CoV-2-induced autoimmune response is unknown and is an active area of interest for the researchers. Objective:: The primary objective of this study is to identify the autoantigen markers for the classification of SARS CoV-2 (COVID-19 positive and negative samples) that trigger an immune response leading to autoimmunity using a machine learning approach that provides information to obtain a more accurate diagnosis for COVID-induced diseases. Materials and Methods:: Our study reports the transcriptomic profile of the COVID patient's whole blood samples collected from 0 to 35th day of acute infection as described in the GSE215865 dataset. The binary classification algorithm from the sci-kit learn python library, namely logistic regression and random forest with 10-fold cross-validation, was applied to the processed data, followed by a selection of the 20 best gene features with recursive feature elimination from a set of 10,719 gene features to obtain the classification accuracy of 87%. Results:: The fidgetin, microtubule severing factor (FIGN), SH3 and cysteine-rich domain (STAC), Cadherin-6 (CDH6), docking protein 6 (DOK6), nuclear RNA export factor 3 (NXF3) and maternally expressed 3 (MEG3) are the autoantigens markers identified for classification of COVID-positive and negative samples. Conclusion:: The identified autoantigen markers from transcriptomic datasets using machine learning techniques provide a deeper understanding of COVID-induced diseases and may play an important role as potential diagnostic and drug targets for COVID-19.

An efficient method for bearing fault diagnosis

Statistical features and wavelet based fault detection are attempted to find computationally less complex, low-memory, and power for real-time implementation. The mean absolute value (MAV), simple sign integral (SSI), waveform length (WL), slope sign change, and zero crossing are extracted from the vibration signal, phase current signal-1, and phase current signal-2. The extracted features are combined varyingly to obtain 31 combinations and classified using a decision tree, k-nearest neighbor {k-NN}, and support vector machine. The identified features {MAV, SSI, WL} performed better with vibration and combined current signals, with an average accuracy of 99.8% and 99.5% with the k-NN classifier, respectively. Wavelet has shown an accuracy of 98%, and the Alexnet method obtained an average accuracy of 97.5% using a combined current signal, which is less than the time domain features-based machine learning approach. In addition, simple time-domain features require memory of 9.6 MB times less than wavelets and 4.18MB times less than Alexnet. The time domain-based technique requires a computation time of 30.21 minutes less than Alexnet and 53.54 minutes less than wavelets. Experimentally, the effectiveness of identified minimal features is verified using an induction motor current signal and achieved 100% accuracy with {MAV, SSI, WL}.

Artificial intelligence-enabled electrocardiography contributes to hyperthyroidism detection and outcome prediction

BackgroundHyperthyroidism is frequently under-recognized and leads to heart failure and mortality. Timely identification of high-risk patients is a prerequisite to effective antithyroid therapy. Since the heart is very sensitive to hyperthyroidism and its electrical signature can be demonstrated by electrocardiography, we developed an artificial intelligence model to detect hyperthyroidism by electrocardiography and examined its potential for outcome prediction.MethodsThe deep learning model was trained using a large dataset of 47,245 electrocardiograms from 33,246 patients at an academic medical center. Patients were included if electrocardiograms and measurements of serum thyroid-stimulating hormone were available that had been obtained within a three day period. Serum thyroid-stimulating hormone and free thyroxine were used to define overt and subclinical hyperthyroidism. We tested the model internally using 14,420 patients and externally using two additional test sets comprising 11,498 and 596 patients, respectively.ResultsThe performance of the deep learning model achieves areas under the receiver operating characteristic curves (AUCs) of 0.725–0.761 for hyperthyroidism detection, AUCs of 0.867–0.876 for overt hyperthyroidism, and AUC of 0.631–0.701 for subclinical hyperthyroidism, superior to a traditional features-based machine learning model. Patients identified as hyperthyroidism-positive by the deep learning model have a significantly higher risk (1.97–2.94 fold) of all-cause mortality and new-onset heart failure compared to hyperthyroidism-negative patients. This cardiovascular disease stratification is particularly pronounced in subclinical hyperthyroidism, surpassing that observed in overt hyperthyroidism.ConclusionsAn innovative algorithm effectively identifies overt and subclinical hyperthyroidism and contributes to cardiovascular risk assessment.

Investigation of influential variations among variables in daylighting glare metrics using machine learning and SHAP

Previous studies have shown the inconsistent performance of various daylighting glare prediction metrics in office daylit-dominated environments. This lack of consensus may stem from a limited understanding of how their component variables contribute to the prediction power reflected on these discomfort glare models. Previous studies predominantly focused on individual variables' linear, independent impact on glare discomfort prediction, neglecting to explore their non-linear and interaction contributions. This study addressed these limitations by evaluating regularly used glare variables using machine learning-based feature selection and SHAP interpretation methods to parse the collected dataset in a subjective survey. By applying different machine learning algorithms and SHAP explainers, we have identified their contribution importance to the prediction of different scales of glare discomfort rating when incorporated into one model and have observed the difference of interaction effects between these variables on predicting glare discomfort ratings. Our findings indicate that vertical eye illuminance, maximal luminance, and window mean luminance exhibit strong prediction power and significant interaction effects on glare discomfort sensations, indicating that they could be the dominant contributors to glare predictive metrics. Contrast effect variables within the field of view had less predictive influence on glare scales when combined with other variables. This innovative approach enables a comprehensive assessment of different variables' influential sequence and interaction consequences when incorporated into the glare prediction model. It facilitates the development of the new glare discomfort prediction model.

Clinical features-based machine learning models to separate sexually transmitted infections from other skin diagnoses

Many sexual health services are overwhelmed and cannot cater for all the individuals who present with sexually transmitted infections (STIs). Digital health software that separates STIs from non-STIs could improve the efficiency of clinical services. We developed and evaluated a machine learning model that predicts whether patients have an STI based on their clinical features. We manually extracted 25 demographic features and clinical features from 1315 clinical records in the electronic health record system at Melbourne Sexual Health Center. We examined 16 machine learning models to predict a binary outcome of an STI or a non-STI diagnosis. We evaluated the models' performance with the area under the ROC curve (AUC), accuracy and F1-scores. Our study included 1315 consultations, of which 36.8% (484/1315) were diagnosed with STIs and 63.2% (831/1315) had non-STI conditions. The study population predominantly consisted of heterosexual men (49.5%, 651/1315), followed by gay, bisexual and other men who have sex with men (GBMSM) (25.7%), women (21.6%) and unknown gender (3.2%). The median age was 31 years (intra-quartile range (IQR) 26-39). The top 5 performing models were CatBoost (AUC 0.912), Random Forest (AUC 0.917), LightGBM (AUC 0.907), Gradient Boosting (AUC 0.905) and XGBoost (AUC 0.900). The best model, CatBoost, achieved an accuracy of 0.837, sensitivity of 0.776, specificity of 0.831, precision of 0.782 and F1-score of 0.778. The key important features were lesion duration, type of skin lesions, age, gender, history of skin disorders, number of lesions, dysuria duration, anorectal pain and itchiness. Our best model demonstrates a reasonable performance in distinguishing STIs from non-STIs. However, to be clinically useful, more detailed information such as clinical images, may be required to reach sufficient accuracy.